VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published 14 days ago • 179
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 23 days ago • 340
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants Paper • 2607.26611 • Published Jul 29 • 33
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published Jul 29 • 140
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Paper • 2607.21553 • Published Jul 23 • 39
Spectral Rewiring for Exploration, Purification, and Model Merging Paper • 2607.03065 • Published Jul 3 • 25
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Image-Text-to-Text • 35B • Updated Apr 17 • 1.5M • 3.62k
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon Paper • 2607.01804 • Published Jul 2 • 31
Is Position Bias in Dense Retrievers Built In-or Learned from Data? Paper • 2605.26578 • Published May 26 • 21
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence Paper • 2605.30093 • Published May 28 • 16